© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158968
    Prev
    Next
    INDEX
    Explanations

    peristaltic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ו
    1.43
    ق
    1.40
    و
    1.34
    もら
    1.34
    も
    1.29
    一
    1.22
    すでに
    1.16
    ;
    1.14
    在
    1.13
    t
    1.11
    POSITIVE LOGITS
    ong
    1.38
    1.25
    were
    1.14
    aren
    1.13
    ag
    1.12
    ok
    1.06
    ur
    1.05
     are
    1.05
    sch
    1.03
    usal
    1.03
    Activations Density 0.001%

    No Known Activations